Testing Procedure for Item Response Probabilities of 2Class Latent Model
Journal: Mehran University Research Journal of Engineering and Technology (Vol.39, No. 3)Publication Date: 2020-07-01
Authors : Bushra Shamshad; Junaid Sagheer Siddiqui;
Page : 657-667
Keywords : Latent Class Model; Hotelling T2; Maximum Likelihood; Bootstrapping; EM Algorithm; goodness of fit test; Bartlett Test;
Abstract
This paper presents Hotelling T2 as a procedure for the testing of significance difference between the item response probabilities (ωij′s) of classes in a Latent Class Model (LCM). Parametric bootstrap technique is used in order to generate samples for ωij′s. These samples are based on the estimated parameters of 2-class latent model. The estimation of parameters in either situation is done using the Expectation Maximization (EM) algorithm through Maximum likelihood method. The hypothesis under consideration is whether the response probabilities (ωij′s) are equal against each item in both the classes. { H0 : ωi1 = ωi2. against H1 : =ωi1 ≠ ωi2}. If the test exhibits significant difference between response probabilities in both classes, it will be a clear indication of a presence of latent variable. We consider both training and testing data sets to develop the test. In order to apply Hotelling T2 test the basic assumptions of normality and homogeneity of variance are also checked. Chi-square goodness of fit test is used for assessing normal distribution to be good fitted on the hypothesized (bootstrap samples) based on 2-class latent model parameters for each data and Bartlett test to check heterogeneity of variances in ωij′s. Moreover, our procedure produces a minimum standard error of estimates as compared to those obtained through the package in R.Gui environment
Other Latest Articles
- Analyzing the Effects of Data Augmentation on Single and Multimodal Biometrics
- A Framework for Optimization of Power Consumption in Mobile Computing Devices
- A Wideband and Efficient Patch Antenna with Two Different Feeding Mechanisms for Ku/K Bands Applications
- Anonymization Framework for Securing Protected Health Information in a Complex Dataset of Medical Narratives
- Review of Social Media Influence on Software Development
Last modified: 2020-11-15 04:00:26